Train
Tokenizer
cd scripts
python -m venv venv
source venv/bin/activate
pip install -U -r requirements.in
python -B train_tokenizer.py
Dataset
cd scripts
python -m venv venv-lit
source venv-lit/bin/activate
pip install -U -r requirements-lit.in
python -B prepare_pretrain_dataset.py
Model
cd scripts
python -m venv venv-lit
source venv-lit/bin/activate
pip install -U -r requirements-lit.in
litgpt pretrain --config ./model.yaml